Re: Progress on scaling of FreeBSD on 8 CPU systems

On Sun, Feb 25, 2007 at 01:54:20PM +0100, Martin Blapp wrote:

Hi,

It would be really great if we could find "workload owners" who would
maintain easy-to-run benchmark configurations and also run them regularly
on a fixed hardware configuration over a long time publishing results and
testing patches. Kris has done this for SQL benchmarks to great effect,

I'm interested in such a workload test. At my job we run various other
servers which have a classic virus/antispam environment. And unfortunatly
clamd behaves not very well on FreeBSD (see mails to freebsd-threads),
and this happens even on 2-CPU systems.

I think its not very difficult to make a scripted load test, with
2/4/6/8/16/32
scans in parallel, with ULE or BSD scheduler.

Btw: what is the best method to profile a threaded application to see where
it
spends the most CPU time ?

If you can package up some kind of test or analogous workload that I
can run, I'd be happy to take a look at profiling it on MP hardware.

Kris

P.S. I assume you've done all the usual things like using libthr
instead of libpthread.

Attachment: pgpk0ltvBkzIl.pgp
Description: PGP signature

Relevant Pages

  • Re: Progress on scaling of FreeBSD on 8 CPU systems
    ... maintain easy-to-run benchmark configurations and also run them regularly on a fixed hardware configuration over a long time publishing results and testing patches. ... And unfortunatly clamd behaves not very well on FreeBSD, and this happens even on 2-CPU systems. ... it spends the most CPU time? ...
    (freebsd-current)
  • Re: Progress on scaling of FreeBSD on 8 CPU systems
    ... maintain easy-to-run benchmark configurations and also run them regularly on a fixed hardware configuration over a long time publishing results and testing patches. ... And unfortunatly clamd behaves not very well on FreeBSD, and this happens even on 2-CPU systems. ... it spends the most CPU time? ...
    (freebsd-hackers)
  • Re: Progress on scaling of FreeBSD on 8 CPU systems
    ... maintain easy-to-run benchmark configurations and also run them regularly on a fixed hardware configuration over a long time publishing results and testing patches. ... Kris has done this for SQL benchmarks to great effect, ... clamd behaves not very well on FreeBSD, ...
    (freebsd-current)
  • Re: Progress on scaling of FreeBSD on 8 CPU systems
    ... maintain easy-to-run benchmark configurations and also run them regularly on a fixed hardware configuration over a long time publishing results and testing patches. ... Kris has done this for SQL benchmarks to great effect, ... clamd behaves not very well on FreeBSD, ...
    (freebsd-hackers)